Google Inc.

Si Si

Yang Li

Sanjiv Kumar

Lukasz Mieczyslaw Kaiser

Samuel Bengio

Cho-Jui Hsieh

Pei-Hung Chen

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing an area attention layer in a neural network system. The area attention layer area implements a way for a neural network model to attend to areas in the memory, where each area contains a group of items that are structurally adjacent.

Neural networks with area attention

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for decreasing neural network inference times using softmax approximation. One of the methods includes maintaining data specifying a respective softmax weight vector for each output in a vocabulary of possible neural network outputs; receiving a neural network input; processing the neural network input using one or more initial neural network layers to generate a context vector for the neural network input; and generating an approximate score distribution over the vocabulary of possible neural network outputs for the neural network input, comprising: processing the context vector using a screening model configured to predict a proper subset of the vocabulary for the context input; and generating a respective logit for each output that is in the proper subset, comprising applying the softmax weight vector for the output to the context vector.

Decreasing neural network inference times using softmax approximation

Growing community of inventors

San Jose, CA, United States of America

Si Si